JP2010178747A - Deracemisation of amines - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To a method for enantiomeric conversion of amines by enzyme treatment. <P>SOLUTION: The method for the enantiomeric conversion of amines includes treating a chiral amine or a mixture of amine enantiomers with a Type II amine oxidase enzyme (e.g. Aspergillus niger monoamine oxidase) capable of catalysing oxidation of the amine in a stereoselective manner and, subsequently or simultaneously, treating with a reducing agent. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a method for deracemization or chiral inversion of chiral amines by enzymatic treatment of enantiomeric mixtures. The method uses stereoselective enzymatic conversion and non-selective or partially selective chemical or enzymatic conversion simultaneously or sequentially. The present invention also provides methods for the selection of suitable enzymes, particularly suitable amine oxidases, and methods for the production of novel enzymes suitable for use in the above deracemization method.

  Enantiomerically pure chiral amines are valuable synthetic intermediates, especially for the preparation of pharmaceutical target molecules. Traditionally, chiral amines form one salt of the enantiomer by a separation method such as diastereomeric crystallization using a chiral acid, or by a physical method (1) such as intersolvent partitioning or chromatography. It has been obtained by kinetic resolution of racemates using enzymes that react selectively with one enantiomer, making separation easier. Such a process can achieve a high enantiomeric excess (e.e.), but only gives up to 50% of the racemic starting material as the required enantiomer. Like many chiral compounds, all can yield products with 100% yield and 100% ee in principle, including asymmetric approaches or resolution and racemates of undesired enantiomers. There is an increasing demand for the development of synthetic strategies for amines that combine with crystallization. Asymmetric methods that have been suggested to date include the use of transaminases to convert ketones to chiral amines (2,3,4). Furthermore, the kinetic resolution of amines using lipases such as Burkholderia plantarii lipase (5,6) or Candida antarctica (7) can be used to form imines (5,6) or transfer hydrogenation using Pd / C as a catalyst ( Combined with racemization of unreacted amine according to 7).

  Another approach, called deracemization, involves the steric inversion of one enantiomer to the other, for example using a periodic oxidation-reduction chain. To date, it has been shown that such systems can be applied to the preparation of L-α-amino acids using enantioselective D-amino acid oxidases in combination with non-selective reducing agents. In the first work (8), sodium borohydride was used as a reducing agent, and the steric inversion from D-alanine to L-alanine was reported although the yield was low. The instability of sodium borohydride at pH 7 has hindered its use on a practical scale, and in recent years we have developed sodium cyanoborohydride (13), Pd / C. It has been shown that amino acid deracemization can be performed more efficiently using ammonium formate containing and more suitable reducing agents including borohydride complexes or amine: boranes (14). However, there are no examples of successful application of deracemization to amines to date.

  The present invention relates to the deracemization or chiral inversion of chiral amines by treating a mixture of amine enantiomers with an enzyme that can stereoselectively catalyze the oxidation of amines, and subsequently or simultaneously treating the mixture with a reducing agent. In the specification generally referred to as enantiomeric transformations). The method of the invention is applicable to various ratios of enantiomeric mixtures, including racemic mixtures, and to the conversion from one single enantiomer to the other (epimerisation). For example, the method may be a 1: 1, 1: 2, 1: 5, 1:10, 2: 1, 5: 1, 10: 1, 100: 1 or other ratio mixture of R and S type amines. It is applicable to. The product of the enantiomeric transformation is richer in the desired enantiomer than the starting material. That is, the desired enantiomer is in enantiomeric excess. Preferably the product comprises a substantially pure single enantiomer. Thus, in a preferred embodiment, the enantiomeric conversion method of the present invention is used to convert a mixture of amine enantiomers into a composition consisting essentially of a single enantiomer. Alternatively, using the enantiomeric conversion method of the present invention, one substantially pure amine enantiomer is converted to the other, again in enantiomerically pure form.

  The reducing agent may be partially stereoselective or non-stereoselective, and may be a chemical reducing agent. Alternatively, the reduction may be catalyzed by an enzyme. If a chemical reducing agent is to be used, the reducing agent is selected from transfer hydrogenation reagents such as sodium borohydride, sodium cyanoborohydride, amine: borane complex or ammonium formate containing Pd / C. It can be advantageous. If the stereoselective oxidation and the non-stereoselective (or partially selective) reduction are subsequently performed in an oxidation-reduction cycle, the cycle may be performed multiple times until the desired enantiomeric excess is achieved. good.

  The enzyme capable of stereoselectively catalyzing amine oxidation may be monoamine oxidase (MAO), particularly microbial monoamine oxidase, but any amine oxidase enzyme may be used. One of the MAOs that can be advantageously used in the methods of the present invention is by incorporating one or more mutations into the Aspergillus niger monoamine oxidase or variants thereof, for example, particularly in the region of amino acids 25-265 and 334-350. In which the enzyme is different from wild type A. nigerMAO, particularly preferably an enzyme having a mutation in one or more of amino acids 259, 260, 336 and 348, more particularly an enzyme having a mutation N336S or a double mutation N336S, M348K. is there.

The present invention also provides
a) mutating the originator enzyme to produce at least one enzyme variant,
b) screening the enzyme variants for activity against homochiral substrates, and c) selecting one or more enzymes that exhibit increased activity against homochiral substrates over the original enzyme.
Provides a way to guide the evolution of the original enzyme. Optionally, steps a), b) and c) may be repeated using the enzyme variant selected in step (step) c) as the original enzyme. At an appropriate stage, enzyme variants may be assayed against the opposite enantiomer of the substrate or against a mixture of substrate enantiomers to confirm enantioselectivity. In certain embodiments, the original enzyme is an oxidase that is active against an amine, such as an amine oxidase, particularly a monoamine oxidase. The substrate can be any chiral amine that can be oxidized to an imine, including a cyclic secondary amine, for example an amine of formula I.

[Where:
a) R is H or C _1-4 alkyl and R 1 and R 2 are independently substituted or unsubstituted C _1-10 alkyl, C _1-10 alkenyl, C _1-10 cycloalkyl, C _1-10 Telocycle, C _1-10 aryl, C _1-10 heteroaryl, C _1-4 alkyl-aryl, C _1-4 alkyl-heteroaryl, C _1-4 alkyl-C _1-6 cycloalkyl and C _1-4 Selected from alkyl-C _1-6 heterocycles, or b) R is H or C _1-4 alkyl, R 1 and R 2 taken together may contain one or more heteroatoms, substituted or unsubstituted A C _1-10 cycloalkyl ring system or a C _1-10 aryl ring, or c) R and R 1 taken together can contain one or more heteroatoms, substituted or unsubstituted C _{1- A 10} cycloalkyl or C _1-10 aryl ring system is formed and R 2 is as defined above a)].

  As used herein, the term “halo” or “halogen” refers to fluorine, chlorine, bromine and iodine.

As used herein, the term “alkyl” refers to a straight or branched hydrocarbon chain containing the specified number of carbon atoms. For example, C ₁ -C ₃ alkyl means a straight or branched hydrocarbon chain containing at least 1 and at most 3 carbon atoms. Examples of alkyl as used herein include, but are not limited to, methyl, ethyl, n-propyl, i-propyl.

  As used herein, the term “cycloalkyl” refers to a fully saturated hydrocarbon ring containing the specified number of carbon atoms. The term “cycloalkyl” includes monocyclic and bicyclic structures. Examples of cycloalkyl as used herein include, but are not limited to, cyclohexyl, cyclopropyl.

  The term “aryl” as used herein refers to an unsaturated compound that can be a saturated or unsaturated hydrocarbon ring containing the specified number of carbon atoms. The term “aryl” includes monocyclic and bicyclic structures. Examples of aryl used herein include, but are not limited to, phenyl and naphthyl.

  If the cycloalkyl or aryl ring system contains one or more heteroatoms, these are selected from N, S or O, preferably N. Thus, the terms “heterocyclic” and “heteroaryl” refer to cycloalkyl and aryl groups containing up to 3 heteroatoms, each selected from N, S or O, preferably N.

When one or more of R, R 1 and R 2 or the ring formed between them is substituted, there can be 1 to 3 substituents, which are halogen, hydroxy, C _1-3 alkyl, C ₁ Selected from _-3 alkenyl, C _1-3 alkoxy, nitro, nitrile and CONH ₂ .

  Conveniently, the target substrate can be used for the evolution of an enzyme with improved activity and enantioselectivity for that particular substrate.

  Thus, the present invention provides a method for improving the catalytic activity, and possibly the enantioselectivity of amine oxidases, in particular monoamine oxidases, by directed evolution including enzyme mutations and selection of mutants with improved activity against homochiral substrates. To do. Also provided is the use of an enzyme variant selected by such a method in a method for deracemization or epimerization of amines.

  The wild-type amino acid sequence of A. niger MAO is shown in SEQ ID NO: 1. In one embodiment, the present invention relates to wild type A. niger by incorporation of the enzyme in the region of amino acids 334-350, in particular amino acid 336 and / or amino acid 348, more specifically the mutant N336S or the double mutant N336S, M348K. A variant of A. niger MAO that differs from MAO is provided. Thus, the present invention provides a variant of A. niger MAO having the amino acid sequence shown in SEQ ID NO: 2, and in a further embodiment, a variant of A. niger MAO having the amino acid sequence shown in SEQ ID NO: 3.

  Throughout this specification and the appended claims, unless the context indicates otherwise, the words “including” and “including” and “including” variations such as the stated number or step or number or It will be understood that it includes a group of stages but does not exclude other numbers or stages or groups of numbers or stages.

  A chiral compound has two or more enantiomers that are stereochemically different. A composition comprising two or more enantiomers of a chiral compound is termed a “racemic mixture” if it contains equal or substantially equal amounts of enantiomers. In contrast, a composition is “homochiral”, “enantiomerically pure” or comprises a single enantiomer substantially free of the corresponding enantiomer, or consists essentially of one enantiomer without the other enantiomer, or “Substantially pure single enantiomer”. “Substantially pure” means that the corresponding enantiomer is present in less than about 5% by weight, in particular less than about 3% by weight, and even less than about 1% by weight. “Enantioselective” and “stereoselective” are used interchangeably herein and refer to the tendency of a reaction in which one enantiomer of a chiral compound is favored over the other. “Partially stereoselective” (or “partially enantioselective”), “non-enantioselective” and the like should be understood accordingly.

The reaction scheme of the oxidation-reduction cycle leading to deracemization is shown. Figure 4 schematically illustrates an assay used to detect an enzyme having the desired enantioselective amine oxidase activity. FIG. 3 shows the results of 27 enzymes selected in the detection assay of FIG. 2 assayed against L-AMBA and D-AMBA. The substrate specificity of N336S and M348K mutant A. niger monoamine oxidase is shown. Fig. 3 shows enantioselectivity of N336S, M348K mutant A. niger monoamine oxidase.

  The present invention will now be described in more detail with reference to the accompanying drawings and sequence listing.

  SEQ ID NO: 1 shows the amino acid sequence of the wild-type Aspergillus niger monoamine oxidase enzyme (Note: We found that the sequence differs by 4 amino acids from that reported by Schilling & Lerch (10,11)) These differences are probably due to errors in the original DNA sequencing, two of which are also pointed out by Sablin (12)).

  SEQ ID NO: 2 This shows the amino acid sequence of a mutant monoamine oxidase enzyme prepared by directed evolution in the examples. Mutation N336S is shown in bold and underlined.

  SEQ ID NO: 3 This shows the amino acid sequence of a mutant monoamine oxidase enzyme prepared by site-directed mutagenesis of the N336S mutant enzyme of SEQ ID NO: 2. Mutations N336S and M348K are shown in bold and underlined.

  Here we report a significant new extension of deracemization, with the first application to chiral amine deracemization. The reaction follows the general scheme shown in FIG. Since the enzyme preferentially reacts with one of the two chiral forms, it converts one enantiomer to the other and leaves the other unreacted. The enzymatic reaction produces an achiral imine that does not have a chiral center at the carbon attached to the nitrogen. Non-selective reduction of the imine results in a 1: 1 mixture of amine enantiomers (a non-equal mixture of amine enantiomers is formed when a partially selective reducing agent is used). When this step is performed in multiple cycles, the amine approaches enantiomeric purity (which becomes a sufficiently enantioselective amine oxidase). If the imine can be efficiently reduced before hydrolysis to the ketone occurs, the yield can approach 100%.

  Amine oxidases are classified into two groups, type I (Cu / TOPA dependent) and type II (flavin dependent) (15). In the catalytic cycle of the type I enzyme, the intermediate imine remains covalently bound to the protein, mitigating interference at this stage in the reaction of reducing the imine back to the amine. Type II enzymes have been studied exclusively with mammalian origin (9), but type II enzymes of microbial origin have not been well documented, and in fact, at the beginning of our research, enantioselective transformation There was no report about. Schilling et al. (10, 11) reported the cloning and expression of type II monoamine oxidase (MAO-N) from Aspergillus niger, then Sablin et al. (12) purified the enzyme to homogeneity, substrate specificity and kinetics. The study was conducted. The enzyme has been reported to be highly active against simple aliphatic amines (eg amylamine, butylamine), but to a lesser extent also against benzylamine.

  Our studies show that the A. niger MAO-N enzyme has very low but measurable activity on L-α-methylbenzylamine and the oxidation of the D-enantiomer is much slower Became. This enzyme is therefore partially enantioselective. The present inventors performed in vitro evolution (16, 17), and produced a novel amine oxidase enzyme with improved catalytic activity and enantioselectivity over the wild type A. niger MAO-N enzyme. We have also shown the applicability of evolved mutants in deracemization reactions.

To create a large library of enzyme variants, we used mutagenized strains for random mutation of plasmids containing inserts encoding wild type A. niger amine oxidase enzyme. Previously, E. coli XL1-Red mutagen (Stratagene) was used for in vitro evolution experiments, but all parts of the plasmid were subject to mutation (reference: error prone PCR only shows the target gene). Mutated), resulting in improved enzyme production and altered enzyme activity and / or specificity. After transforming the plasmid library into E. coli BL21 cells, multiple cycles were performed with the mutagenized strain, and a library of about 10 ⁶ mutants could be generated.

  As mutant enzymes were produced, they were assayed for amine oxidase activity. Amine oxidase is typical of all members of the oxidase family in that it releases hydrogen peroxide as a byproduct. Much of what has been reported in assays for oxidase activity utilizes hydrogen peroxide production in combination with peroxidase, particularly in the presence of a substrate that yields a product that is clearly colored upon oxidation. We first used aminoantipyrine / tribromohydroxybenzoic acid as a substrate for peroxidase to obtain a clear pinkish red colony that can be easily visualized. However, the colored product is relatively soluble so that the color from the active colonies diffuses quickly and the background intensity increases. This problem was overcome by switching the substrate to 3,3'-diaminobenzazine (DAB) which yielded a dark pink insoluble product, resulting in a very high definition and contrast of active colonies. . It should be noted that this high throughput screening is generally applicable not only to amine oxidase but also to other oxidase enzymes.

  This library was plated directly on a nitrocellulose filter on an agar plate (approximately 3,000 colonies per plate) and a screening protocol was followed using a subset of the plate (see FIG. 2). Each filter was transferred to a Petri dish and stored at −20 ° C. for 24-72 hours to partially lyse the cells. Each plate was then treated at 60 ° C. with a cocktail containing both the assay mixture and 2% agarose. Plates were incubated for 24-48 hours at 37 ° C., after which positive clones were examined and then picked, further diluted and plated onto plates to isolate pure colonies.

  Screening the first library subset (about 150,000 clones) identified 35 clones with improved activity against L-AMBA compared to the wild-type enzyme. Each of these clones was grown on a small scale and assayed for both L- and D-AMBA as a cell-free extract, resulting in the best 27 clones for further study. Selected. Each of these 27 was assayed against L-AMBA and D-AMBA and the results are shown in FIG. Finally, mutant enzyme clones that showed the greatest improvement over the wild-type enzyme in terms of their selectivity for L-AMBA versus D-AMBA and activity were selected for more detailed experiments. Additional mutations were then introduced to increase expression.

  Codons used in DNA and RNA to encode amino acids are known to exhibit certain overlaps (degeneracy). Thus, an amino acid may be encoded by two or more three base codons. However, an organism may use one of the alternative codons for a particular amino acid more commonly than the other. This is relevant when introducing heterologous nucleic acids into the host organism for expression. Sometimes the codons used in the original organism are “more unfavorable” codons for the host, and as a result expression can be difficult, such as reduced expression levels. Similarly, certain amino acids may be less presented in the proteome of an organism compared to other organisms. It may be possible to increase the level of heterologous expression in the host cell by using alternative nucleic acid sequences to exchange unfavorable codons and / or amino acids for a more preferred alternative. The present invention provides an isolated nucleic acid that is a variant of A. niger MAO and that encodes a monoamine oxidase enzyme in which the codons for R259 and R260 are optimized for expression in a heterologous host cell. More specifically, if the expression of MAO is intended to occur in E. coli, the amino acid arginine at these positions is replaced with another amino acid of similar charge and size. These mutations can be added to mutations that alter the catalytic activity and / or enantioselectivity of the mutant enzyme. In a further embodiment, an enantioselective monoamine oxidase enzyme that is a variant of A. niger MAO and differs from wild-type A. niger monoamine oxidase by incorporating mutation N336S and one or more of mutations M348K, R259L, and R260L. provide.

  The mutant N336S identified below can be the basis for a “hot spot” mutation that introduces additional mutations in the amino acids around position 336. Mutations can be effected by site-directed mutagenesis, by constructing chimeric recombinant enzymes in a “cut and paste” methodology using restriction enzymes, or by other means well known to those skilled in the art. This method is used to identify additional mutants with increased activity over the N336S mutant, such as the N336S, M348K double mutant identified herein.

[Example 1]
Construction of mutant plasmid DNA library using Escherichia coli XL1-Red mutagen
The Aspergillus niger MAO gene cloned into pET3a was obtained from B. Schilling (11). This gene was amplified by pfu Turbo DNA polymerase using primers designed according to E. coli codon usage. The PCR product was subcloned into the pET16b vector (Novagen). This construct (MAOpET16b) was used for mutagenesis with E. coli XL1-Red mutagen.

  E. coli XL1-Red mutagenized competent cells were obtained from Stratagene. Competent cells were transformed as described in the Stratagene protocol. 700 μl of the transformed cell suspension (Transformation 1) in 20 ml of LB medium (trypton 10 g / L, yeast extract 5 g / L, NaCl 10 g / L, pH 7) containing ampicillin (100 μg / ml; LB Amp) Inoculated and grown for 18 hours at 37 ° C. in a 50 ml Falcon tube in an incubator shaker. These growth conditions were used throughout the experiment.

  20 μl of growing culture was inoculated into 10 ml of fresh LB Amp and allowed to grow for 24 hours. The plasmid was purified from 1 ml of culture (Qiagen Plasmid DNA Miniprep Kit) (pMAO2) and used for the second transformation of the mutagen (transformation II). The entire transformed cell suspension was inoculated into 10 ml LB Amp and allowed to grow for 24 hours. Plasmid was purified from 1 ml culture (pMAOretr1.1). 10 ml of LB Amp was inoculated with 100 μl of a growing culture of transformation II. The culture was grown for 24 hours and the plasmid was purified (pMAOretr1.2) and used for transformation III. The entire transformed cell suspension (1 ml) was inoculated into 10 ml LB Amp, grown for 24 hours and the plasmid purified (pMAOretr2.1). 100 μl of growing culture of transformation III was inoculated into another 10 ml LB Amp, grown for 24 hours, the plasmid was purified from 1 ml culture (pMAOretr2.2) and used for transformation IV. The entire suspension of transformed cells (1 ml) was used to inoculate 10 ml of LB Amp, grown for 24 hours, and the plasmid was purified from 1 ml of culture (pMAOretr3.1). 100 μl of growing culture of transformation IV was used to inoculate a new 10 ml LB Amp, grown for 24 hours and the plasmid purified (pMAOretr3.2).

  Escherichia coli BL21 (DE3) was transformed with the pool of the mutated plasmid DNA (pMAOretr2.2, pMAOretr3.1, pMAOretr3.2) to express the mutated MAO gene, and L-α-methylbenzylamine ( L-AMBA) activity was detected.

[Example 2]
A MAO variant screening plate assay (FIG. 2) was used to identify MAO variants having activity against L-AMBA. More specifically, E. coli BL21 (DE3) transformants (2500 colonies per plate) were plated on HiBond-C Extra (Amersham Pharmacia) membranes mounted on LB Amp agar plates and incubated at 37 ° C. for 24 hours. . Membranes containing colonies were removed from the plates, placed at −20 ° C. for 24 hours and incubated with the assay mixture for 24 hours at room temperature.

Assay mixture
1 tablet of DAB (3,3′-diaminobenzidine, Sigma, D-4418) 1 ml of potassium phosphate buffer (1M, pH 7.6)
L-AMBA (10 mM) 30 μl
Horseradish peroxidase (Sigma) 1 mg / ml 30 μl
10% 2% agarose (Bio-Rad)
Water up to 20 ml Positive clones were subjected to a second round of screening (100-200 colonies per plate) to confirm activity.

Example 3
Activity study
a) In a clone selection plate assay, 27 positive clones identified as having improved activity against L-AMBA compared to the wild type enzyme were grown on a small scale and against both L-AMBA and D-AMBA Assayed. One colony of E. coli BL21 (DE3) transformed with the protein expression vector pET16b having the target gene was inoculated into 10 ml of LB Amp and cultured for 24 hours while shaking in a 50 ml Falcon tube. At the end of the incubation, 1 ml of cell culture is centrifuged, the pellet is resuspended in 1 ml of 25 mM potassium phosphate buffer pH 7.6, 0.1 ml is used and both L- and D-AMBA are substrate As a hydrogen peroxide formation assay.

Assay mixture : (Manfred Braun et al., Applied Microbiology and Biotechnology (1992) 37: 594-598)
Phosphate buffer solution (1M, pH7.6) 5ml
2,4,6-Tribromohydrobenzoic acid (2% in DMSO) 500 μl
4-Aminoantipurine (1M) 37.5μl
L- or D-AMBA (final concentration 5 mM) 32.5 μl
Up to 50 ml of water
The following was added to the 895 μl assay mixture:
5 μl of HRP (Sigma, P6782) (1 mg / ml)
Sample (100 μl) was added and after 24 hours the absorbance at 510 nm was measured against a control without sample. The absorbance results are shown in FIG.

  Some of these 27 clones show increased protein expression when visualized on polyacrylamide gels and are clearly expression variants (data not shown). The best mutant plasmid identified showed no significant increase in expression but its selectivity for L-vs D-AMBA and a significant improvement over the wild-type enzyme in terms of activity. Growing on a larger scale, the enzyme was purified. The wild-type enzyme was also purified using the same protocol and the substrate specificity and enantioselectivity were compared for the two enzymes.

  The mutated gene was also sequenced and the sequence is shown in SEQ ID NO: 2. In the wild type enzyme, the asparagine at position 336 was replaced with serine and there was a single amino acid change.

b) Growth and comparison of mutant and wild type enzymes
Growth and purification of MAO mutants expressed in E. coli BL21 (DE3)
LB medium (6 × 300 ml) containing ampicillin (100 μg.ml ⁻¹ ) in a 1 L baffled flask was inoculated with a single colony of monoamine oxidase mutant from the LB agar plate. The culture was incubated at 30 ° C. for 22 hours (OD ₆₀₀ -3.6), then harvested and washed with phosphate buffer (50 mM, pH 8) to give a tan pellet (11.2 g).

The pellet was resuspended in Tris / HCl buffer (25 mM, pH 7.8, 30 ml) and sonicated on ice (30 seconds on, 30 seconds off for 10 minutes). The suspension was then centrifuged (20,000 rpm, 4 ° C.) until a clear supernatant was obtained, and the supernatant was dialyzed against Tris / HCl buffer (25 mM, pH 7.8). The cell-free extract was filtered through a 0.45 μm sterile membrane and chromatographed on a QSepharose anion exchange column. Fractions were assayed using a colorimetric method based on hydrogen peroxide and the active fractions were stored at -80 ° C. Active fractions had a protein content of 1mg.ml ^-1, specific activity 0.193U.Mg ^-1 for amylamine.

Chromatographic conditions:
Column = HiFlow QSepharose 26/10
Buffer A = Tris / HCl (25 mM, pH 7.8)
Buffer B = Tris / HCl (25 mM, pH 7.8) + 1 M NaCl
Flow rate = 4ml.min ^-1
Fraction collection = 10ml
Column wash = 2CV 100% buffer A
Elution = 10CV 100% Buffer A to 100% Buffer B
Column wash = 4CV 100% buffer B
Assay mixture phosphate buffer (1M, pH7.6) 5ml
2,4,6-Tribromo-3-hydroxybenzoic acid (2% in DMSO) 500 μl
4-Aminoantipyrine (1.5 M) 37.5 μl
30 μl of amine substrate (final concentration 0.015-5 mM)
Water 44.4ml
Assay conditions Assay mixture 990 μl
Horseradish peroxidase (1mg.ml- ¹ ) 5μl
10 μl enzyme
The spectrophotometer was blanked for the assay mixture and HRP. Enzyme was added and absorbance at 500 nm was measured for 10 minutes at 3 second intervals.

result:

Km values were calculated using “KaleidaGraph for Windows” (Synergy Software). For the calculation of K _cat, the active enzyme concentration was determined by estimating the FAD content from the absorbance at 458 nm using an attenuation coefficient of 11 mM ⁻¹ cm ⁻¹ (see ref 12).

  The data shows that the activity of mutant amine oxidase (kcat = 8.0min-1) against L-AMBA is 47 times higher than that of wild type (kcat = 0.17min-1). Furthermore, the selectivity of the mutant for L-enantiomer versus D-AMBA (about 100: 1) was also increased compared to the wild-type enzyme (about 17: 1). Thus, as a result of in vitro evolution experiments, both the enantioselectivity and catalytic activity of the enzyme were improved simultaneously. For comparison, the activities for the best substrates with wild-type enzymes, namely amylamine and benzylamine are listed. In chiral HPLC (Chiralcel CrownPak CR +), complete oxidation of the L-enantiomer was apparent after 24 hours, whereas no conversion of the D-enantiomer could be detected, resulting in substantial activity and selectivity of the mutant. Improvement was confirmed.

Example 4
Deracemization reaction
DL-AMBA was used as a substrate, and various reducing agents were screened in the presence of mutant MAO-N (sodium borohydride, catalytic transfer hydrogenation, amine: boranes). This screening identified ammonia: borane as the optimal reagent with a D-AMBA yield of 77% and an enantiomeric excess of 93%. A higher optical purity of the product (up to 99% ee) could be achieved, but in that case the yield was low.

More specifically, MAO mutant N336S (0.193 U.ml ⁻¹ 100 μl = 0.02 U) DL-AMBA (0.13 μl, final concentration = 0.8 mM) and ammonia-borane complex (4 M solution 10 μl, final) Concentration = 80 mM, 100 eq) was added to a phosphate buffer solution (400 μl, 20 mM, pH 8). A 10 μl aliquot was diluted with 990 μl perchloric acid, pH 1.5 and analyzed by HPLC. The reaction mixture was incubated at 30 ° C. and the reaction was monitored by HPLC at regular intervals until no further reaction was observed.

D-AMBA yield = 77%, ee = 93%:
Analysis conditions : Column = Chiralcel CrownPak CR +
Mobile phase = 100% perchloric acid, pH 1.5
Flow rate = 0.8ml.min ^-1
Detection = 200nm
Temperature = 25 ° C
rt (L-AMBA) = 12.8 minutes
rt (D-AMBA) = 16.5 minutes

Example 5
Stereoinversion reaction We also performed stereoinversion from L-AMBA to D-AMBA (yield 18%, 99% ee) and under the same conditions from D-AMBA to L-AMBA. Indicates that no conversion occurs.

More specifically, MAO mutant N336S (0.193 U.ml ⁻¹ 100 μl = 0.02 U) L-AMBA (0.13 μl, final concentration = 0.4 mM) and ammonia-borane complex (4 M solution 10 μl, final It was added to a phosphate buffer solution (400 μl, 20 mM, pH 8) at a concentration = 80 mM, 200 eq). A 10 μl aliquot was diluted with 990 μl perchloric acid, pH 1.5 and analyzed by HPLC. The reaction mixture was incubated at 30 ° C. and the reaction was monitored by HPLC at regular intervals until no further reaction was observed.

D-AMBA yield = 18%, ee> 99%:
NB: When D-AMBA was used as a substrate under the same reaction conditions, no reaction was observed after 24 hours.

Analysis conditions : Column = Chiralcel CrownPak CR +
Mobile phase = 100% perchloric acid, pH 1.5
Flow rate = 0.8ml.min ^-1
Detection = 200nm
Temperature = 25 ° C
rt (L-AMBA) = 12.8 minutes
rt (D-AMBA) = 16.5 minutes
Analysis of the HPLC chromatogram suggests that the yield in the deracemization reaction is prevented from reaching 100% due to the formation of byproducts with longer retention times as the reaction proceeds. We are currently optimizing the deracemization protocol to achieve the high levels of yield and selectivity previously reported in the deracemization of α-amino acids.

Abbreviations:
MAO-monoamine oxidase
AMBA-α-methylbenzylamine
TBHBA-2,4,6-tribromo-3-hydroxybenzoic acid
AAP-4-aminoantipyrine
HRP-horseradish peroxidase type VI derived from bovine liver
LB−Lubria Bertani
rt-retention time

Example 6
Substrate Specificity of N336S Mutant Enzyme The activity of the above mutant enzyme was examined for various amine substrates. The assay conditions were essentially as shown in Example 3. The substrates tested were as follows:

result:

Example 7
Generation of additional mutant clones The first published sequence of the wild-type A. niger monoamine oxidase indicated a lysine at position 348. Some of the mutant enzymes prepared above and first tested in Example 3 (a) were considered double mutants because of having a methionine at this position. However, when the wild type sequence was confirmed (resequenced), the amino acid at position 348 of the wild type was shown to be methionine (as shown in SEQ ID NO: 1). To elucidate the effects of mutations at this site (if any), site-directed mutagenesis was performed on the wild-type enzyme to introduce the M348K mutation. The identity of the amino acid at this position affects the expression efficiency. In the case of lysine, the expression increases without changing the catalytic activity of the enzyme (the absolute activity U / ml is higher than the wild type, but when corrected for the amount of protein, The same K _cat value as that of the wild-type enzyme was obtained). Subsequent site-directed mutagenesis of the above N336S mutant to generate a second mutation (M348K) combines the increased catalytic ability of the N336S mutation with increased expression. The amino acid sequence of this double mutant is shown in SEQ ID NO: 3.

Example 8
Substrate specificity of N336S and M348K mutant enzymes The activity of the above double mutant enzymes was examined for various amine substrates. The assay conditions were essentially those shown in Example 3. The tested substrates and relative conversion rates (comparison with L-AMBA as 100) are shown in FIG. For some substrates, both enantiomers were tested as substrates. In all cases, the enzyme clearly showed enantioselectivity and in some cases no activity against the opposite enantiomer was detectable (enantioselectivity data is shown in FIG. 5).

Example 9
Application of expression of mutant R260K It was found that the mutant R260K is in a codon with a low incidence of arginine. Sequencing revealed that all “expressed” mutants had the same mutation at position 260 where arginine was replaced with lysine.

  The wild-type MAO-N amino acid sequence has two arginines at positions 259 and 260 encoded by a low-occurrence (4%) codon (AGG) in the E. coli gene. Lysine and arginine are both basic amino acids, and therefore, the charge of the protein is not affected by substitution of one of them for the other, but Arg's low frequency codon AGG (4%) is Lys' high frequency codon AAG (22 %), Protein expression in E. coli is improved. Therefore, the inventors decided to replace the codons of both Arg259 and Arg260 with the codon CGT (38%) by site-directed mutagenesis to evaluate the effect on the expression level of MAO-N. Another approach would be to create “silent” mutations by changing the AGG codon to a different codon (AGA, CGT, CGC, CGA, CGG) that also encodes arginine.

表３ 部分精製MAO WT及びMAOArg259/260におけるアミルアミン（AA）に対する比活性 MAO WT and MAOArg259 / 260 were partially purified from recombinant E. coli BL21 (DE3) carrying pET16b carrying the corresponding mao-n gene. Cell-free extracts were prepared by sonication and the specific activity of MAO WT and MAOArg259 / 260 against AA was measured for both soluble and insoluble fractions (Table 3).

Table 3 Specific activities for partially purified MAO WT and MAOArg259 / 260 against amylamine (AA)

To confirm an increase in R260K mutant expression level, cell-free extracts of MAO WT, mutant 4 (R260K) and MAOArg259 / 260 were obtained and assayed against L-AMBA. This was done by incubating 50 μl of each sample for 240 minutes and measuring the specific activity (Table 4).

In conclusion, the inventors have significantly expanded their deracemization strategy by applying it for the first time to the deracemization of chiral amines. By doing so, we have successfully achieved a “directed evolution” of the enzyme to meet the special requirements of the new biotransformation. Another interesting aspect of the invention is the identification of highly enantioselective variants by using a single enantiomeric substrate (L-AMBA) in the screen. There has been much debate about the need for a truly enantioselective screening that uses racemates, thereby mimicking the real situation found in kinetic optical resolution where two enantiomers compete for the enzyme. . If it is possible to screen a very large and diverse library of different genes (eg 10 ⁶ ), the enantioselectivity is selected by the methods described herein using essentially simpler screening. It will be possible.

  The application of which this description and claims forms part may be used as a basis for priority in subsequent applications. The claims of such subsequent application may be for any feature or combination of features described herein. They may take the form of product claims, composition claims, method claims or use claims and may include, as non-limiting examples, one or more of the appended claims.

References
(1) LE Iglesias, VM Sanchez, F. Rebolledo and V. Gotor, Tetrahedron: Asymmetry (1997) 8, 2675-2677.
(2) JS Shin, BG Kim, A. Liese and C. Wandrey, Biotechnol. Bioeng. (2001) 73 179-187;
(3) G. Matcham, M. Bhatia, W. Lang, C. Lewis, R. Nelson, A. Wang and W. Wu, Chimia (1999) 53, 584-589;
(4) JS Shin, BG Kim, Biotechnol. Bioeng., (1999) 65, 206-211.
(5) G. Hieber and K. Ditrich, Chimica Oggi (2001) 19, 16-20;
(6) F. Balkenhohl, K. Ditrich, B. Hauer and W. Ladner, J. Prakt. Chem. (1997) 339, 381.
(7) MT Reetz and K. Schimossek, Chimia, (1996), 50, 668-669.
(8) EW Hafner and D. Wellner, Proc. Nat. Acad. Sci. (1971) 68, 987.
(9) RB Silverman, JM Cesarone and X. Liu, J. Am. Chem. Soc. (1993) 115, 4955.
(10) B. Schilling and K. Lerch, Biochim. Biophys. Acta. (1995), 1243, 529.
(11) B. Schilling and K. Lerch, Mol. Gen. Genet. (1995) 247, 430.
(12) SO Sablin, V. Yankovskaya, S. Bernard, CN Cronin and TP Singer, Eur. J. Biochem. (1998) 253, 270.
(13) T Beard and NJ Turner Chem. Commun. 2002 (printing)
(14) FR Alexandre, DP Pantaleone, PP Taylor, IG Fotheringham, DJ Ager and NJ Turner (2002) Tetrahedron Lett. 43, 707-710.
(15) PL Dostert, MS Benedetti and KF Tipton (1989) Medicinal Research Reviews 9, 45-89.
(16) JD Sutherland (2000) Curr. Opinion. Chem. Biol. 263.
(17) FH Arnold (1998) Acc. Chem. Res. 31, 125.

Claims (12)

Formula I:

[Where:
a) R is H or C _1-4 alkyl and R 1 and R 2 are independently substituted or unsubstituted C _1-10 alkyl, C _1-10 alkenyl, C _1-10 cycloalkyl, C _1-10 Telocycle, C _1-10 aryl, C _1-10 heteroaryl, C _1-4 alkyl-aryl, C _1-4 alkyl-heteroaryl, C _1-4 alkyl-C _1-6 cycloalkyl and C _1-4 alkyl -C _1-6 is selected from heterocycle, or b) R is H or C _1-4 alkyl, substituted or unsubstituted R1 and R2 contains one or more hetero atoms together Form a C _1-10 cycloalkyl ring system or a C _1-10 aryl ring, or c) R and R 1 taken together can contain one or more heteroatoms, substituted or unsubstituted C _1-10 A cycloalkyl or C _1-10 aryl ring system is formed, and R 2 is as defined above a)]
Or a mixture of amine enantiomers of the formula I is treated with a type II amine oxidase enzyme capable of catalyzing the oxidation of the amine in a stereoselective manner followed by treatment with a reducing agent. Enantiomeric conversion method.   The method of claim 1, which is an epimerisation of one amine enantiomer to the other.   The process of claim 1 wherein the amine enantiomer mixture is a racemic mixture.   4. A process according to any one of claims 1 to 3, wherein the reducing agent is partially enantioselective.   The method according to any one of claims 1 to 4, wherein the reducing agent is a chemical reducing agent and is not enantioselective.   6. The method of claim 5, wherein the reducing agent is selected from sodium borohydride, sodium cyanoborohydride, an amine: borane complex or a transfer hydrogenation reagent.   7. The method of claim 6, wherein the transfer hydrogenation reagent is ammonium formate containing Pd / C.   7. The method of claim 6, wherein the amine: borane complex is an ammonia: borane complex.   The method according to any one of claims 1 to 8, comprising an oxidation-reduction cycle in which the step of treating with an enzyme capable of catalyzing the oxidation of amine and the step of treating with a reducing agent are carried out a plurality of times successively.   10. The enzyme according to any one of claims 1 to 9, wherein the enzyme is a mutant form of A. niger type II monoamine oxidase which differs from wild type A. niger type II monoamine oxidase by mutation in the region of amino acids 334-350. Method.   11. The method of claim 10, wherein the enzyme is a variant of A. niger type II monoamine oxidase that differs from wild type A. niger type II monoamine oxidase by mutation of amino acid number 336.   12. The method of claim 11, wherein the enzyme is a variant of A. niger type II monoamine oxidase that differs from wild type A. niger type II monoamine oxidase by incorporation of mutation N336S.

Images